تقرير
iNVS: Repurposing Diffusion Inpainters for Novel View Synthesis
العنوان: | iNVS: Repurposing Diffusion Inpainters for Novel View Synthesis |
---|---|
المؤلفون: | Kant, Yash, Siarohin, Aliaksandr, Vasilkovsky, Michael, Guler, Riza Alp, Ren, Jian, Tulyakov, Sergey, Gilitschenski, Igor |
سنة النشر: | 2023 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computer Vision and Pattern Recognition |
الوصف: | We present a method for generating consistent novel views from a single source image. Our approach focuses on maximizing the reuse of visible pixels from the source image. To achieve this, we use a monocular depth estimator that transfers visible pixels from the source view to the target view. Starting from a pre-trained 2D inpainting diffusion model, we train our method on the large-scale Objaverse dataset to learn 3D object priors. While training we use a novel masking mechanism based on epipolar lines to further improve the quality of our approach. This allows our framework to perform zero-shot novel view synthesis on a variety of objects. We evaluate the zero-shot abilities of our framework on three challenging datasets: Google Scanned Objects, Ray Traced Multiview, and Common Objects in 3D. See our webpage for more details: https://yashkant.github.io/invs/ Comment: Accepted to SIGGRAPH Asia, 2023 (Conference Papers) |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2310.16167 |
رقم الأكسشن: | edsarx.2310.16167 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |